Commit 516a3204 authored by Daniel Campora's avatar Daniel Campora
Browse files

Updated readmes.

parent 76e29b5d
Pipeline #1651519 passed with stages
in 17 minutes and 15 seconds
Configuring the sequence of algorithms
======================================
`Allen` centers around the idea of running a __sequence of algorithms__ on input events. This sequence is predefined and will always be executed in the same order.
Allen centers around the idea of running a __sequence of algorithms__ on input events. This sequence is predefined and will always be executed in the same order.
The sequence can be configured with python. Existing configurations can be browsed under `configuration/sequences`. The sequence name is the name of each individual file, without the `.py` extension, in that folder. For instance, some sequence names are `velo`, `ut`, or `hlt1_pp_default`.
......
......@@ -23,7 +23,7 @@ __global__ void saxpy(float *x, float *y, int n, float a) {
We want to add the algorithm to a specific folder inside the `device` folder:
```
```console
device
├── associate
│   ├── CMakeLists.txt
......@@ -46,14 +46,14 @@ device
Let's create a new folder inside the `device` directory named `example`. We need to modify `device/CMakeLists.txt` to reflect this:
```cmake=
```cmake
add_subdirectory(raw_banks)
add_subdirectory(example)
```
Inside the `test` folder we will create the following structure:
```
```console
├── test
│   ├── CMakeLists.txt
│   └── example
......@@ -65,7 +65,7 @@ Inside the `test` folder we will create the following structure:
The newly created `test/CMakeLists.txt` file should reflect the project we are creating. We can do that by populating it like so:
```cmake=
```cmake
file(GLOB saxpy_sources "src/*cu")
include_directories(include)
......@@ -86,7 +86,7 @@ If your new algorithm does not use any Velo related objects, this is not necessa
The includes of main, gear and sequence are required for any new algorithm in Allen.
Link the new library "Examples" to the stream library in `stream/CMakeLists.txt`:
```cmake=
```cmake
target_link_libraries(Stream PRIVATE
CudaCommon
Associate
......
......@@ -11,14 +11,14 @@ we show a proposed development setup with CVMFS and CentOS 7:
* CPU target: Any modern compiler can be used, such as gcc greater than 7.0:
```shell
```console
source /cvmfs/sft.cern.ch/lcg/views/setupViews.sh LCG_97python3 x86_64-centos7-gcc8-opt
```
* CUDA target: The latest supported compilers are gcc-8 and clang-6. CUDA is
available in cvmfs as well:
```shell
```console
source /cvmfs/sft.cern.ch/lcg/views/setupViews.sh LCG_97python3 x86_64-centos7-gcc8-opt
source /cvmfs/sft.cern.ch/lcg/contrib/cuda/10.2/x86_64-centos7/setup.sh
```
......@@ -28,7 +28,7 @@ we show a proposed development setup with CVMFS and CentOS 7:
* CUDACLANG target: A version of the clang compiler with ptx support is required,
alongside a local installation of CUDA 10.1 (currently latest supported release):
```shell
```console
source /cvmfs/sft.cern.ch/lcg/releases/clang/10.0.0/x86_64-centos7/setup.sh
```
......@@ -53,7 +53,7 @@ If other inputs are required, follow these instructions for producing them:
Allen selections require ODIN banks, which were not included with these samples. Random ODIN banks can be generated using `makeODIN.py`. From the Allen root directory:
```shell
```console
python3 scripts/makeODIN.py /path/to/data/banks/
```
......@@ -153,7 +153,7 @@ The results of the tests are published in this [mattermost channel](https://matt
For local throughput measurements, we recommend the following settings in Allen standalone mode:
```
```console
nvprof ./Allen -f /scratch/allen_data/201907/minbias_mag_down -n 1000 -m 700 -r 100 -t 12 -c 0
```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment